© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12626
    Prev
    Next
    INDEX
    Explanations

    code and mathematical notations

    oai_token-act-pair · gemini-2.0-flash

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.84
     myſelf
    -0.79
     saites
    -0.75
    Portail
    -0.73
    InjectAttribute
    -0.71
    الحياه
    -0.70
    ніципалі
    -0.68
    RenderAtEndOf
    -0.68
    felves
    -0.68
    neſs
    -0.68
    POSITIVE LOGITS
     OFDb
    0.47
    唑
    0.46
    omyces
    0.45
    fta
    0.45
     here
    0.45
    mi
    0.43
     review
    0.43
     f
    0.43
     at
    0.43
     plane
    0.42
    Activations Density 1.153%

    No Known Activations